Linear means straight line. If we want to solve any problem with a line model, it will be a linear model. Linear regression is the method of predicting real value of a dependent variable based on independent variables. It represents with a straight line. y=mx+c
y=means dependent variables , m=means Coefficient/slope of the line ,x=means independent variables, c=means intercept
#Multiple Linear Regression
Multiple linear regression refers a linear relationship between a single output with multiple input.
#Formula for multiple linear regression Y = β0 + β1x1 + β2x2 + ..... + βpxp
#Decision Tree
Decision tree is a type of classification algorithm which comes under the supervised learning technique. Decision trees usually start from a single node and then branch into possible outcomes. Each of these results leads to other nodes, which branch into other possibilities. This gives it a tree-like shape. Decision trees are used for handling non-linear data sets effectively. Decision trees can be divided into two types; categorical variable and continuous variable decision trees
#Entropy
Entropy measures the impurity or uncertainty present in the data. It is used to decide how a Decision Tree can split the data.
#Information Gain
Information Gain (IG) is the most significant measure used to build a Decision Tree.
The formula of decision tree – Information Gain I(p,n) : {(-p / p+n) log2 (p / p+n)} – {(n / p+n) log2 (n /p+n)}
b) Entropy (c) {(-p / p+n) log2 (p / p+n)} – {(n / p+n) log2 (n /p+n)}
c) Entropy E(a) ∑ pi +ni/p+n *I (pi, ni)
d) Gain, G(A) Entropy (c) - Entropy E(a)
Gradient Descent
Gradient Descent most commonly used optimization algorithms to train machine learning models by means of minimizing errors between actual and expected results. Further, gradient descent is also used to train Neural Networks.
m = m — learning rate * ∂/∂m = m — α * ∂/∂m
b = b — learning rate * ∂/∂b = b — α * ∂/∂b